HLSTM: Heterogeneous Long Short-Term Memory Network for Large-Scale InSAR Ground Subsidence Prediction

Abstract

Accurate prediction of ground subsidence is of great significance for the prevention and mitigation of this type of geological disaster. It is still a challenge when wide area is concerned. In this article, a heterogeneous long short-term memory (HLSTM) network is proposed for large-scale ground subsidence prediction based on interferometric synthetic aperture radar (InSAR) data. First, the study area is divided into homogeneous subregions through spatial clustering of InSAR-derived subsidence velocity. Second, a specific LSTM model is constructed to capture complex nonlinear temporal correlations embedded in InSAR-derived subsidence time series for each subregion. Essentially both spatial heterogeneity and temporal correlation are incorporated into the HLSTM prediction. In the experiment part, the HLSTM predictor is validated using a subsidence monitoring result from 80 Sentinel-1 images acquired over Cangzhou, China, from 2017 to 2019. The HLSTM result shows the highest prediction accuracy through comparisons with the results from other seven methods.

Keywords

• Deep learning
• heterogeneity
• interferometric synthetic aperture radar (InSAR)
• long short-term memory (LSTM)
• subsidence prediction